ausboss/llama7b-wizardlm-unfiltered-4bit-128g

Lora fine tune trained on this dataset

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{data_point["instruction"]}

### Response:
{data_point["output"]}

CUDA_VISIBLE_DEVICES=0 python llama.py model c4 --wbits 4 --true-sequential --groupsize 128 --save_safetensors 4bit-128g.safetensors